© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45716
    Prev
    Next
    INDEX
    Explanations

    slow change or progression

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sudden
    -1.56
    早く
    -1.46
     segera
    -1.34
     rapid
    -1.29
     schnell
    -1.27
     suddenly
    -1.24
     speedy
    -1.23
     instantly
    -1.23
     briefly
    -1.21
     cepat
    -1.21
    POSITIVE LOGITS
     but
    1.91
     Slowly
    1.70
     slowly
    1.70
    Slowly
    1.39
     gradually
    1.34
     dần
    1.28
    慢慢
    1.23
    越来越
    1.16
     lentement
    1.13
     steadily
    1.09
    Activations Density 0.025%

    No Known Activations